Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:183622a5ab893a5daf04c9b1b26c0d551e6142da089cc352972d2c15142576ab
+oid sha256:575e3f8ca94f970a14db711e2d985a4428183bf5d917685c93630ffdf2023a17
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ac8cccd415a40dbb631c4e7f5f88bb68fb4021e2c036fdfc9908e93d6350696
+oid sha256:d31f994d1199047e9fc25fd2d3996d2c26a8f12551fc74e27fcc796c2013f503
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:582e0098e8d99cf77f28c52c568c3601751ed0bcc51f02e1d09509f030003379
+oid sha256:5ce6951ffe304a17c96bd88a9e270d66267e06be1493240275c127819b315cc5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c188a6a4749e6ca627bb6d536eb7443f499d5b1b88d98a78f9c713443e010d9c
+oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.2354156970977783,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.04672897196261682,
+  "best_metric": 2.1007940769195557,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.09345794392523364,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 17.286,
       "eval_steps_per_second": 8.738,
       "step": 10
+    },
+    {
+      "epoch": 0.056074766355140186,
+      "grad_norm": 1.0673582553863525,
+      "learning_rate": 0.000163742398974869,
+      "loss": 2.2537,
+      "step": 12
+    },
+    {
+      "epoch": 0.07009345794392523,
+      "grad_norm": 0.9949750304222107,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 2.2227,
+      "step": 15
+    },
+    {
+      "epoch": 0.07009345794392523,
+      "eval_loss": 2.146998167037964,
+      "eval_runtime": 5.2815,
+      "eval_samples_per_second": 17.23,
+      "eval_steps_per_second": 8.71,
+      "step": 15
+    },
+    {
+      "epoch": 0.08411214953271028,
+      "grad_norm": 0.9237583875656128,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 2.0809,
+      "step": 18
+    },
+    {
+      "epoch": 0.09345794392523364,
+      "eval_loss": 2.1007940769195557,
+      "eval_runtime": 5.2667,
+      "eval_samples_per_second": 17.278,
+      "eval_steps_per_second": 8.734,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3709436417802240.0,
+  "total_flos": 7418872835604480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null